# Computations
import numpy as np
import pandas as pd
import pickle

# Visualisation libraries

## Text
from colorama import Fore, Back, Style
from IPython.display import Image, display, Markdown, Latex, clear_output

## progressbar
import progressbar

## plotly
from plotly.offline import init_notebook_mode, iplot 
import plotly.graph_objs as go
import plotly.offline as py
from plotly.subplots import make_subplots
import plotly.express as px

## seaborn
import seaborn as sns

## matplotlib
import matplotlib.pyplot as plt
from matplotlib.patches import Ellipse, Polygon
from matplotlib.font_manager import FontProperties
import matplotlib.colors as mcolors
plt.style.use('seaborn-whitegrid')
plt.rcParams['axes.labelsize'] = 14
plt.rcParams['xtick.labelsize'] = 12
plt.rcParams['ytick.labelsize'] = 12
plt.rcParams['text.color'] = 'k'
%matplotlib inline

import warnings
warnings.filterwarnings("ignore")

Home / Financial Analysis and Modeling

Statlog (German Credit Data) Dataset

• Preprocessing
• Exploratory Data Analysis
• Modeling: Gradient Boosting Classifier
• Modeling: PyTorch Multi-layer Perceptron (MLP) for Binary Classification

Statlog (German Credit Data) Dataset

In this article, we analyze the UCI Statlog (german credit data) from Kaggle.com.

Context

The original dataset contains 1000 entries with 20 categorial/symbolic attributes prepared by Prof. Hofmann. In this dataset, each entry represents a person who takes a credit by a bank. Each person is classified as good or bad credit risks according to the set of attributes. The link to the original dataset can be found below.

Content

It is almost impossible to understand the original dataset due to its complicated system of categories and symbols. Thus, I wrote a small Python script to convert it into a readable CSV file. Several columns are simply ignored, because in my opinion either they are not important or their descriptions are obscure. The selected attributes are:

• Age (numeric)
• Sex (text: male, female)
• Job (numeric: 0 - unskilled and non-resident, 1 - unskilled and resident, 2 - skilled, 3 - highly skilled)
• Housing (text: own, rent, or free)
• Saving accounts (text - little, moderate, quite rich, rich)
• Checking account (numeric, in DM - Deutsch Mark)
• Credit amount (numeric, in DM)
• Duration (numeric, in month)
• Purpose (text: car, furniture/equipment, radio/TV, domestic appliances, repairs, education, business, vacation/others)

Path = 'Statlog_Dataset/german_credit_data.csv'

def Header(Text, L = 100, C = 'Blue', T = 'White'):
    BACK = {'Black': Back.BLACK, 'Red':Back.RED, 'Green':Back.GREEN, 'Yellow': Back.YELLOW, 'Blue': Back.BLUE,
         'Magenta':Back.MAGENTA, 'Cyan': Back.CYAN}
    FORE = {'Black': Fore.BLACK, 'Red':Fore.RED, 'Green':Fore.GREEN, 'Yellow':Fore.YELLOW, 'Blue':Fore.BLUE,
         'Magenta':Fore.MAGENTA, 'Cyan':Fore.CYAN, 'White': Fore.WHITE}
    print(BACK[C] + FORE[T] + Style.NORMAL + Text + Style.RESET_ALL + ' ' + FORE[C] +
          Style.NORMAL +  (L- len(Text) - 1)*'=' + Style.RESET_ALL)
    
def Line(L=100, C = 'Blue'):
    FORE = {'Black': Fore.BLACK, 'Red':Fore.RED, 'Green':Fore.GREEN, 'Yellow':Fore.YELLOW, 'Blue':Fore.BLUE,
         'Magenta':Fore.MAGENTA, 'Cyan':Fore.CYAN, 'White': Fore.WHITE}
    print(FORE[C] + Style.NORMAL + L*'=' + Style.RESET_ALL)

def Search_List(Key, List): return [s for s in List if Key in s]

Data = pd.read_csv(Path.split(".")[0]+'_Mod.csv')
Header('Standardized Dataset:')
display(Data.head())
display(pd.DataFrame({'Number of Instances': [Data.shape[0]], 'Number of Attributes': [Data.shape[1]]}).style.hide_index())

# Dictionaries
with open(Path.split(".")[0] + '_Feat_Dict.pkl', 'rb') as fp:
    Feat_Dict = pickle.load(fp)
    
Target = 'Risk'
Labels = [x.title() for x in Data[Target].unique()]

def dtypes_group(Inp, Dict = False):
    Temp = Inp.dtypes.to_frame(name='Data Type').sort_values(by=['Data Type'])
    Out = pd.DataFrame(index =Temp['Data Type'].unique(), columns = ['Features','Count'])
    for c in Temp['Data Type'].unique():
        Out.loc[Out.index == c, 'Features'] = [Temp.loc[Temp['Data Type'] == c].index.tolist()]
        Out.loc[Out.index == c, 'Count'] = len(Temp.loc[Temp['Data Type'] == c].index.tolist())
    Out.index.name = 'Data Type'
    Out = Out.reset_index(drop = False)
    Out['Data Type'] = Out['Data Type'].astype(str)
    
    if Dict:
        Out = dict(zip(Out['Data Type'], Out['Features']))
    return Out

dType = dtypes_group(Data, Dict = True)

Standardized Dataset: ==============================================================================

	Age	Sex	Job	Housing	Saving Accounts	Checking Account	Credit Amount	Duration	Purpose	Risk
0	67	Male	2	Own	None	Little	1169	6	Radio/TV	Good
1	22	Female	2	Own	Little	Moderate	5951	48	Radio/TV	Bad
2	49	Male	1	Own	Little	None	2096	12	Education	Good
3	45	Male	2	Free	Little	Little	7882	42	Furniture/Equipment	Good
4	53	Male	2	Free	Little	Little	4870	24	Car	Bad

Number of Instances	Number of Attributes
1000	10

Exploratory Data Analysis

def FeatAgg(Feat, ColorFeat, Target = Target, Inp = Data):
    Out = Inp[[Feat, ColorFeat,Target]]
    Out = Out.groupby([Feat, ColorFeat,Target])[Target].agg({'count'}).rename(columns = {'count':'Count'})
    Out['Percentage'] = np.round(100* Out.values /Out.sum().values, 2)
    Out.reset_index(drop = False, inplace = True)
    Out = Out.sort_values(by=[Feat])
    Out[Feat] = Out[Feat].astype(str)
    return Out

def FeatBins(Inp, Bins, replace = True, String = True):
    Bins = [int(x) for x in Bins]
    Out = pd.cut(Inp, bins = pd.IntervalIndex.from_tuples([(x, y) for x, y in zip(Bins[:-1],Bins[1:])]))
    if replace:
        Out = Out.astype('str').replace(Dict)
    if String:
        Out = Out.astype('str')
        try:
            Out = Out.str.replace(pat = '(-1', repl = '[0')
        except:
            pass
    return Out

def DistPlot(Feat, Target = Target, nbins = 20,
             Colors = ['LightSalmon', 'LightBlue'], LC = 'Black',
             yLim = [0, 80], H = 450, titleY = 0.92, Inp = Data):
    fig = px.histogram(Inp, x = Feat, nbins=nbins, color= Target, marginal= 'box',
                       color_discrete_sequence= Colors, hover_data=Data.columns)
    fig.update_xaxes(showline=True, linewidth=1, linecolor='Lightgray', mirror=True,
                     zeroline=False, zerolinewidth=1, zerolinecolor='Black',
                     showgrid=False, gridwidth=1, gridcolor='Lightgray')
    fig.update_yaxes(showline=True, linewidth=1, linecolor='Lightgray', mirror=True,
                     zeroline=True, zerolinewidth=1, zerolinecolor='Black',
                     showgrid=True, gridwidth=1, gridcolor='Lightgray')
    # Median
    fig.add_trace(go.Scatter(x= Inp[Feat].median()* np.ones(int(yLim[1])), y= np.arange(int(yLim[0]), int(yLim[1])),
                         name="Median", line=dict(color='RoyalBlue', width=2, dash='dot')))
    # Mean
    fig.add_trace(go.Scatter(x= Inp[Feat].mean()* np.ones(int(yLim[1])), y= np.arange(int(yLim[0]), int(yLim[1])),
                         name="Mean", line=dict(color='Red', width=2, dash='dot')))

    Name = '%s Distribution by %s' % (Target, Feat)

    fig.update_layout(legend_orientation='v', plot_bgcolor= 'white', height= H, width= 980,
                     title={'text': '<b>' + Name + '<b>', 'x':0.5, 'y': titleY, 'xanchor': 'center', 'yanchor': 'top'},
                     yaxis_title='Frequency')
    fig.update_traces(marker_line_color= LC, marker_line_width=0.5, opacity=1)
    fig['layout']['yaxis'].update(range=yLim)
    fig.show()
    
def DispPlot2(Feat, ColorFeat, xLim, yLim, Target = Target, nbins = 5, titleY = 0.90, LC = 'Black', H2 = 320, W = 980, 
            Colors1 = ['Pink', 'BlueViolet'], Colors2 = ['OrangeRed', 'LimeGreen'], Inp = Data):
    # Top Figure
    fig = make_subplots(rows=1, cols=2, horizontal_spacing = 0.02, shared_yaxes=True,
                        subplot_titles=('%s: <b>%s<b>' % (Target,Labels[0]), '%s: <b>%s<b>' % (Target,Labels[1])))
    for j in range(2):
        Temp = Inp.loc[Inp[Target] == Labels[j]].sort_values(by = ColorFeat)
        if Colors1 == None:
            figtemp = px.histogram(Temp, x= Feat, color = ColorFeat, nbins = nbins)
        else:
            figtemp = px.histogram(Temp, x= Feat, color = ColorFeat, nbins = nbins,
                                color_discrete_sequence = Colors1)
        for i in range(len(figtemp['data'])):
                       fig.add_trace(figtemp['data'][i], row=1, col=j+1)
        del figtemp, Temp

    fig.update_traces(marker_line_color= LC, marker_line_width=1, opacity=1)
    fig.update_yaxes(title_text ='Frequency', row=1, col=1)
    fig.update_traces(showlegend = False, row=1, col=2)
    fig.update_xaxes(showline=True, linewidth=1, linecolor='Lightgray', mirror=True,
                     zeroline=False, zerolinewidth=1, zerolinecolor='Black',
                     showgrid=False, gridwidth=1, gridcolor='Lightgray', range=xLim)
    fig.update_yaxes(showline=True, linewidth=1, linecolor='Lightgray', mirror=True,
                     zeroline=True, zerolinewidth=1, zerolinecolor='Black',
                     showgrid=True, gridwidth=1, gridcolor='Lightgray', range=yLim)
    fig.update_layout(plot_bgcolor= 'white', barmode='stack', width = W)
    Name = '%s Distribution by %s and %s' % (Feat, ColorFeat, Target)
    fig.update_layout(title={'text': '<b>' + Name + '<b>', 'x':0.5, 'y': titleY, 'xanchor': 'center', 'yanchor': 'top'})
    fig.show() 
    # Bottom Figure
    fig = px.box(Data, x= Feat,  y = ColorFeat, color = Target,
                   color_discrete_sequence= Colors2, hover_data=Data.columns)
    fig.update_traces(quartilemethod='linear')
    fig.update_xaxes(showline=True, linewidth=1, linecolor='Lightgray', mirror=True,
                     zeroline=False, zerolinewidth=1, zerolinecolor='Black',
                     showgrid=False, gridwidth=1, gridcolor='Lightgray', range=xLim)
    fig.update_yaxes(showline=True, linewidth=1, linecolor='Lightgray', mirror=True,
                     zeroline=True, zerolinewidth=1, zerolinecolor='Black',
                     showgrid=True, gridwidth=1, gridcolor='Lightgray')
    fig.update_layout(plot_bgcolor= 'white', barmode='stack', height= H2, width = W)
    fig.show()
    
def PlotX(df, Feat, ColorFeat, Target = Target, Labels = Labels,
           Colors = list(mcolors.TABLEAU_COLORS.values()), LC = 'Black',
           yLim = [0, 35], H = 500, titleY = 0.90):   
    # Figure
    fig = make_subplots(rows=1, cols=2, horizontal_spacing = 0.02, shared_yaxes=True, y_title = 'Percent',
                        subplot_titles=('%s: <b>%s<b>' % (Target, Labels[0]),
                                        '%s: <b>%s<b>' % (Target, Labels[1])))
    # Left
    if Colors == None:
        fig1 = px.bar(df.loc[df[Target] == Labels[0]], x=  Feat, y= 'Percentage', orientation='v',
                      color = ColorFeat, text = 'Percentage', hover_data= df.columns)
    else:
        fig1 = px.bar(df.loc[df[Target] == Labels[0]], x=  Feat, y= 'Percentage', orientation='v',
                      color = ColorFeat, text = 'Percentage', hover_data= df.columns,
                      color_discrete_sequence = Colors)

    for i in range(len(fig1['data'])):
        fig.add_trace(fig1['data'][i], row=1, col=1)
    fig.update_traces(marker_line_color= LC, marker_line_width=1, opacity=1, row=1, col=1)

    # Right
    if Colors == None:
        fig2 = px.bar(df.loc[df[Target] == Labels[1]], x= Feat, y= 'Percentage', orientation='v',
                      color = ColorFeat, text = 'Percentage', hover_data= df.columns)
    else:
        fig2 = px.bar(df.loc[df[Target] == Labels[1]], x= Feat, y= 'Percentage', orientation='v',
                      color = ColorFeat, text = 'Percentage', hover_data= df.columns,
                      color_discrete_sequence = Colors)

    for i in range(len(fig2['data'])):
        fig.add_trace(fig2['data'][i], row=1, col=2)
    fig.update_traces(marker_line_color= LC, marker_line_width=1, opacity=1, showlegend = False, row=1, col=2)

    # Update
    fig.update_xaxes(showline=True, linewidth=1, linecolor='Lightgray', mirror=True,
                     zeroline=False, zerolinewidth=1, zerolinecolor='Black',
                     showgrid=False, gridwidth=1, gridcolor='Lightgray')
    fig.update_yaxes(showline=True, linewidth=1, linecolor='Lightgray', mirror=True,
                     zeroline=False, zerolinewidth=1, zerolinecolor='Black',
                     showgrid=True, gridwidth=1, gridcolor='Lightgray', range= yLim)
    fig.update_layout(legend_orientation='v', legend_title_text=ColorFeat, plot_bgcolor= 'white', height= H, width= 980)
    fig.update_layout(legend=dict(font=dict(color="Black"), bordercolor="Lightgray", borderwidth=1))
    Name = '%s Distribution by %s and %s' % (Target, Feat, ColorFeat)
    fig.update_layout(title={'text': '<b>' + Name + '<b>', 'x':0.5, 'y': titleY, 'xanchor': 'center', 'yanchor': 'top'})
    fig.show() 

df = Data.copy()
for Feat in dType['int64']:
    df[Feat] = FeatBins(Inp = Data[Feat], Bins = Feat_Dict[Feat], replace = False)

Age

Feat = 'Age'
DistPlot(Feat = Feat, Colors = ['LightCoral', 'LimeGreen'], yLim = [0, 250], nbins = 20)


ColorFeat = 'Housing'
Table = FeatAgg(Feat, ColorFeat, Inp = df)
PlotX(Table, Feat, ColorFeat, Target = Target, yLim = [0, 25], Colors = ['RoyalBlue','ForestGreen','Tomato'])

ColorFeat = 'Saving Accounts'
Table = FeatAgg(Feat, ColorFeat, Inp = df).sort_values(by = [ColorFeat])
PlotX(Table, Feat, ColorFeat, Target = Target, yLim = [0, 20], Colors = ['YellowGreen','ForestGreen','Gray', 'Coral','Tomato'])

ColorFeat = 'Checking Account'
Table = FeatAgg(Feat, ColorFeat, Inp = df).sort_values(by = [ColorFeat])
PlotX(Table, Feat, ColorFeat, Target = Target, yLim = [0, 20], Colors = ['YellowGreen','ForestGreen','Gray','Tomato'])

Credit Amount

Feat = 'Credit Amount'
DistPlot(Feat = Feat, Colors = ['LightCoral', 'LimeGreen'], yLim = [0, 400])

DispPlot2(Feat = 'Credit Amount', ColorFeat = 'Sex', xLim = [0 , 22e3], yLim = [0 , 350], nbins = 10,
          Colors1 = ['DeepPink', 'RoyalBlue'], Colors2 = ['LightCoral', 'LimeGreen'], Inp = Data)

ColorFeat = 'Saving Accounts'
Table = FeatAgg(Feat, ColorFeat, Inp = df).sort_values(by = [ColorFeat])
PlotX(Table, Feat, ColorFeat, Target = Target, yLim = [0, 30], Colors = ['YellowGreen','ForestGreen','Gray', 'Coral','Tomato'])

ColorFeat = 'Checking Account'
Table = FeatAgg(Feat, ColorFeat, Inp = df).sort_values(by = [ColorFeat])
PlotX(Table, Feat, ColorFeat, Target = Target, yLim = [0, 30], Colors = ['YellowGreen','ForestGreen','Gray','Tomato'])

Duration

Feat = 'Duration'
DistPlot(Feat = Feat, Colors = ['LightCoral', 'LimeGreen'], yLim = [0, 500], nbins = 10)

ColorFeat = 'Saving Accounts'
Table = FeatAgg(Feat, ColorFeat, Inp = df).sort_values(by = [ColorFeat])
PlotX(Table, Feat, ColorFeat, Target = Target, yLim = [0, 14], Colors = ['YellowGreen','ForestGreen','Gray', 'Coral','Tomato'])

ColorFeat = 'Checking Account'
Table = FeatAgg(Feat, ColorFeat, Inp = df).sort_values(by = [ColorFeat])
PlotX(Table, Feat, ColorFeat, Target = Target, yLim = [0, 10], Colors = ['YellowGreen','ForestGreen','Gray','Tomato'])

Saving Accounts

Feat = 'Saving Accounts'
ColorFeat = 'Purpose'
Table = FeatAgg(Feat, ColorFeat, Inp = Data).sort_values(by = [ColorFeat])
PlotX(Table, Feat, ColorFeat, Target = Target, yLim = [0, 14])

ColorFeat = 'Checking Account'
Table = FeatAgg(Feat, ColorFeat, Inp = df).sort_values(by = [ColorFeat])
PlotX(Table, Feat, ColorFeat, Target = Target, yLim = [0, 20], Colors = ['YellowGreen','ForestGreen','Gray','Tomato'])

---

References

1. Kaggle German Credit Risk Dataset

---